From: Andi Kleen Subject: Re: [PATCH 08/16] ext4: Calculate and verify checksums for inode bitmaps Date: Mon, 5 Sep 2011 20:27:27 +0200 Message-ID: <20110905182727.GH7761@one.firstfloor.org> References: <20110901003030.31048.99467.stgit@elm3c44.beaverton.ibm.com> <20110901003127.31048.13983.stgit@elm3c44.beaverton.ibm.com> <2A834E5A-F07E-4B1E-835B-FBEE3FD7A103@dilger.ca> <20110902191828.GL12086@tux1.beaverton.ibm.com> <8D646179-FD76-4362-A051-8C6ADB3CE1B3@dilger.ca> <20110905182250.GO12086@tux1.beaverton.ibm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Andreas Dilger , Theodore Tso , Sunil Mushran , Amir Goldstein , linux-kernel , Andi Kleen , Mingming Cao , Joel Becker , linux-fsdevel , linux-ext4@vger.kernel.org, Coly Li To: "Darrick J. Wong" Return-path: Content-Disposition: inline In-Reply-To: <20110905182250.GO12086@tux1.beaverton.ibm.com> Sender: linux-fsdevel-owner@vger.kernel.org List-Id: linux-ext4.vger.kernel.org One very interesting optimization would be to profile the metadata workload where you got the slowdown and try to figure out which fields were most commonly updated. If it's some superblock fields or similar maybe those could get their separate crcs that could be separatedly computed at much lower cost. -Andi